© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34909
    Prev
    Next
    INDEX
    Explanations

    ascending order, retrograde direction, market trend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     either
    -1.02
    either
    -0.94
    ijnlijk
    -0.88
     ± 
    -0.88
    EDER
    -0.85
     fave
    -0.85
     wollt
    -0.85
     وغير
    -0.83
     certain
    -0.82
    TODO
    -0.81
    POSITIVE LOGITS
     bias
    0.94
     side
    0.92
     in
    0.92
     çe
    0.90
     Haltung
    0.88
     on
    0.88
     sentiment
    0.86
     (+)
    0.86
     slanted
    0.86
     trend
    0.85
    Activations Density 0.119%

    No Known Activations